diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py
index aabb3bbdf..3c54cabcf 100644
--- a/llama_stack/providers/registry/inference.py
+++ b/llama_stack/providers/registry/inference.py
@@ -24,7 +24,7 @@ META_REFERENCE_DEPS = [
     "zmq",
     "lm-format-enforcer",
     "sentence-transformers",
-    "torchao==0.5.0",
+    "torchao==0.8.0",
     "fbgemm-gpu-genai==1.1.2",
 ]
 
diff --git a/llama_stack/templates/dependencies.json b/llama_stack/templates/dependencies.json
index 053d6ef8a..b96191752 100644
--- a/llama_stack/templates/dependencies.json
+++ b/llama_stack/templates/dependencies.json
@@ -381,7 +381,7 @@
     "sentence-transformers",
     "sentencepiece",
     "torch",
-    "torchao==0.5.0",
+    "torchao==0.8.0",
     "torchvision",
     "tqdm",
     "transformers",